conftrace_

speculative decoding

111 papers

Explore in graph

Also known as

SD

Co-occurring keywords

large language model (13587) inference acceleration (244) inference optimization (219) token generation (47) draft model (21) model compression (3302) model acceleration (80) language model (4599) autoregressive decoding (33) parallel decoding (74)

Papers

LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification ACL 2026
DIAA: A Decoding-Efficient Inference Acceleration Approach for On-Device Large Language Models AAAI 2026
Talon: Breaking the Synchronization Barrier in Speculative Decoding with Hybrid Model-based and Retrieve-based Drafting AAAI 2026
SEED: Accelerating Reasoning Tree Construction via Scheduled Speculative Decoding COLING 2025
Dynamic-Width Speculative Beam Decoding for LLM Inference AAAI 2025
Fuzzy Speculative Decoding for a Tunable Accuracy-Runtime Tradeoff ACL 2025
Multi-Branch Self-Drafting for LLM Inference Acceleration AAAI 2025
Falcon: Faster and Parallel Inference of Large Language Models Through Enhanced Semi-Autoregressive Drafting and Custom-Designed Decoding Tree AAAI 2025
Grouped Speculative Decoding for Autoregressive Image Generation ICCV 2025
CLaSp: In-Context Layer Skip for Self-Speculative Decoding ACL 2025
Cacheback: Speculative Decoding With Nothing But Cache EMNLP 2025
Accelerated Test-Time Scaling with Model-Free Speculative Sampling EMNLP 2025
Hierarchical Speculative Decoding with Dynamic Window NAACL 2025
Spec-VLA: Speculative Decoding for Vision-Language-Action Models with Relaxed Acceptance EMNLP 2025
Faster In-Context Learning for LLMs via N-Gram Trie Speculative Decoding EMNLP 2025
PLD+: Accelerating LLM Inference by Leveraging Language Model Artifacts NAACL 2025
Turning Trash into Treasure: Accelerating Inference of Large Language Models with Token Recycling ACL 2025
SpecCoT: Accelerating Chain-of-Thought Reasoning through Speculative Exploration EMNLP 2025
Amphista: Bi-directional Multi-head Decoding for Accelerating LLM Inference NAACL 2025
Decoding Speculative Decoding NAACL 2025
Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference EMNLP 2025
EMS-SD: Efficient Multi-sample Speculative Decoding for Accelerating Large Language Models NAACL 2025
Speculative Diffusion Decoding: Accelerating Language Generation through Diffusion NAACL 2025
Constrained Decoding with Speculative Lookaheads NAACL 2025
Draft Model Knows When to Stop: Self-Verification Speculative Decoding for Long-Form Generation EMNLP 2025